search

HiLab-git / SSL4MIS

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.
MIT License
2.19k stars 387 forks source link

question about adversarial_network_2D.py #32

Closed JessicaChanzc closed 2 years ago

JessicaChanzc commented 2 years ago

Thank you for the work!

These is a quesiton I would like to ask about, I am trying to run the train_adversarial_network_2D. I am confused about the input of DAN, which shown in the following line, DAN_outputs = DAN(outputs_soft[args.labeled_bs:], volume_batch[args.labeled_bs:]) https://github.com/HiLab-git/SSL4MIS/blob/e8c8b5c5ad36d22748ab7c5745e275f612b1186a/code/train_adversarial_network_2D.py#L158-L159

In your code, you took the output of model(softmax prediction) and unlabeled data as input for FCDiscriminator, but would you pls tell me why?

Thank you.

Luoxd1996 commented 2 years ago

Hi, I am so sorry, recently, I am too busy to reply to many issues/confusions one by one. You can modify it in your understanding or read these original papers. Best, Xiangde.